codex-tokens-compress: Instructions file for Codex

AGENTS.md

codex-tokens-compress AGENTS.md is an instructions file for Codex, OpenCode from LuckyKuang/codex-tokens-compress. It costs 611 tokens per session, scanned B, original, MIT.

Project instructions for compressing AGENTS.md files, which give coding agents rules for working in a repository. The project measures whether shorter, denser instructions improve rule retrieval and reduce token use.

In plain words
What is it for?
Creating, compressing, or updating AGENTS.md files and following the project’s repository, language, and configuration conventions.
Why use it?
It helps keep agent instructions concise while preserving important rules and reducing the amount of text an agent must process.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: reads ~/.codex or $CODEX_HOME, but also the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md; mentions Codex.

This is LuckyKuang/codex-tokens-compress's own configuration. It tells Codex and OpenCode how to work on codex-tokens-compress itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codex-tokens-compress configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LuckyKuang/codex-tokens-compress. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/LuckyKuang/codex-tokens-compress/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/LuckyKuang/codex-tokens-compress

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for codex-tokens-compress AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/luckykuang/codex-tokens-compress/agents-md/github.svg)](https://agentmods.dev/instructions/luckykuang/codex-tokens-compress/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/luckykuang/codex-tokens-compress/agents-md"><img src="https://agentmods.dev/badge/instructions/luckykuang/codex-tokens-compress/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for codex-tokens-compress AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/luckykuang/codex-tokens-compress/agents-md"><img src="https://agentmods.dev/badge/instructions/luckykuang/codex-tokens-compress/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 611 This file is loaded in full into every session.
When invoked 611 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00611 $0.00611
Opus 5 $0.00305 $0.00305
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 9d ago against content hash 4bd0c9da11aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

codex-tokens-compress AGENTS.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

|Official Dir Facts:mcp/config=`~/.codex/config.toml` or `.codex/config.toml`|trusted project loads `.codex/config.toml` from repo root to cwd|nearer directory overrides farther directory.
AGENTS.md · 28 lines

What it actually says

AGENTS.md

|IMPORTANT: Prefer retrieval-led reasoning over pre-training-led reasoning for any project tasks. |Project:codex-tokens-compress |Primary Goal:Compress AGENTS.md into high-density index rules|increase instruction hit rate|reduce hallucination|save token usage. |Language Policy:规则说明默认中文|path/command/file/code-id保持英文|mandatory IMPORTANT line保留英文原文. |Repo Root:./:{.agents,.codex} |Local Skills:.agents/skills:{agents-md-compress,skill-creator} |Skill Trigger:Use agents-md-compress when request mentions AGENTS.md creation, compression, or rule updates. |Official Dir Facts:repo skills=.agents/skills|user skills=$HOME/.agents/skills|admin skills=/etc/codex/skills|system skills are built in Codex. |Official Dir Facts:project subagents=.codex/agents|user subagents=~/.codex/agents. |Official Dir Facts:mcp/config=~/.codex/config.toml or .codex/config.toml|trusted project loads .codex/config.toml from repo root to cwd|nearer directory overrides farther directory. |Project Constraint:This repo stores project configuration in .codex/config.toml and project skills in .agents/skills. |Compression Format:line-1 must be title|all non-empty lines after title must start with ||prefer Category:path:{...} and Category:value1|value2. |Allowed Content:structure|commands|constraints|verification gates|PR checklist. |Forbidden Content:long narrative|tutorial-style explanation|code fence|##|###. |Anti Hallucination:Never invent paths, commands, rules, or tool outputs. |Anti Hallucination:If a fact cannot be verified from repository files, mark it as Unknown and request confirmation before execution. |Anti Hallucination:Validate key paths and commands before writing or updating index lines. |Evidence Priority:repo files > existing AGENTS.md > local skill references > user explicit input. |Command Index:Validate=python .agents/skills/agents-md-compress/scripts/example.py AGENTS.md |Fallback Validate:check title|check IMPORTANT line|check prefix ||check no ##/###/code fence. |Token Strategy:one-line-one-rule|merge same-type short rules|delete duplicate wording|avoid examples unless requested. |Output Strategy:default concise|only actionable facts|no repeated context. |Change Workflow:extract highest-priority facts|rewrite to index lines|run validation|fix failures. |PR Checklist:scope of rule changes|validation evidence|risk note. |Maintenance Trigger:new module or renamed path|build/test command changed|non-empty lines exceed 35. |Owner:Maintainers update this file when workflow, structure, or constraints change.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 28 lines · 611 tokens per session scan B 4bd0c9da11aa

Subscribe to this mod's changes

codex-tokens-compress AGENTS.md is an instructions file published in the GitHub repository LuckyKuang/codex-tokens-compress (100 stars, last pushed 5mo ago), licensed MIT. It adds 611 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens